{"total":798,"rows":[{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894,"area":"lr"},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437,"area":null},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311,"area":null},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309,"area":"safety"},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218,"area":null},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214,"area":null},{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181,"area":null},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2406.09948","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","created":"2024-06-14","cited_by_count":173,"area":null},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152,"area":null},{"id":"2101.00204","title":"BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla","created":"2021-01-01","cited_by_count":125,"area":null},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120,"area":null},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116,"area":null},{"id":"2104.12250","title":"XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond","created":"2021-04-25","cited_by_count":114,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102,"area":null},{"id":"2205.02022","title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation","created":"2022-05-04","cited_by_count":98,"area":null},{"id":"2401.01055","title":"LLaMA Beyond English: An Empirical Study on Language Capability Transfer","created":"2024-01-02","cited_by_count":95,"area":null},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94,"area":null},{"id":"2110.06341","title":"Learning Compact Metrics for MT","created":"2021-10-12","cited_by_count":93,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2302.01398","title":"The unreasonable effectiveness of few-shot learning for machine translation","created":"2023-02-02","cited_by_count":91,"area":"lr"},{"id":"2212.09535","title":"BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting","created":"2022-12-19","cited_by_count":90,"area":null},{"id":"2309.07462","title":"Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?","created":"2023-09-14","cited_by_count":88,"area":null},{"id":"2402.16694","title":"HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2310.13132","title":"Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries","created":"2023-10-19","cited_by_count":82,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2503.10497","title":"MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation","created":"2025-03-13","cited_by_count":79,"area":"lr"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75,"area":null},{"id":"2306.15162","title":"YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus","created":"2023-06-27","cited_by_count":75,"area":null},{"id":"2309.16575","title":"A Benchmark for Learning to Translate a New Language from One Grammar Book","created":"2023-09-28","cited_by_count":75,"area":null},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75,"area":null},{"id":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68,"area":null},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2201.08277","title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","created":"2022-01-20","cited_by_count":64,"area":null},{"id":"2212.08620","title":"POTATO: The Portable Text Annotation Tool","created":"2022-12-16","cited_by_count":64,"area":null},{"id":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2411.14198","title":"Why do language models perform worse for morphologically complex languages?","created":"2024-11-21","cited_by_count":62,"area":null},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58,"area":null},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2404.16816","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","created":"2024-04-25","cited_by_count":56,"area":null},{"id":"2406.08818","title":"Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination","created":"2024-06-13","cited_by_count":56,"area":null},{"id":"2207.06991","title":"Language Modelling with Pixels","created":"2022-07-14","cited_by_count":55,"area":null},{"id":"2210.08523","title":"Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World","created":"2022-10-16","cited_by_count":55,"area":null},{"id":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2303.13592","title":"Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages","created":"2023-03-23","cited_by_count":51,"area":null},{"id":"2305.14288","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","created":"2023-05-23","cited_by_count":51,"area":"lr"},{"id":"2501.17047","title":"How Linguistics Learned to Stop Worrying and Love the Language Models","created":"2025-01-28","cited_by_count":51,"area":null},{"id":"2305.13820","title":"An Open Dataset and Model for Language Identification","created":"2023-05-23","cited_by_count":50,"area":null},{"id":"2410.15522","title":"M-RewardBench: Evaluating Reward Models in Multilingual Settings","created":"2024-10-20","cited_by_count":50,"area":"alignment"},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2109.11406","title":"Named Entity Recognition and Classification on Historical Documents: A Survey","created":"2021-09-23","cited_by_count":47,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2210.09984","title":"Making a MIRACL: Multilingual Information Retrieval Across a Continuum of Languages","created":"2022-10-18","cited_by_count":47,"area":null},{"id":"2305.16171","title":"Multi-lingual and Multi-cultural Figurative Language Understanding","created":"2023-05-25","cited_by_count":47,"area":null},{"id":"2211.03263","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages","created":"2022-11-07","cited_by_count":46,"area":null},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2203.09435","title":"Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation","created":"2022-03-17","cited_by_count":44,"area":null},{"id":"2311.07978","title":"AfroBench: How Good are Large Language Models on African Languages?","created":"2023-11-14","cited_by_count":43,"area":null},{"id":"2406.03368","title":"IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models","created":"2024-06-05","cited_by_count":43,"area":null},{"id":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43,"area":null},{"id":"2205.11081","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","created":"2022-05-23","cited_by_count":42,"area":null},{"id":"2208.11761","title":"IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages","created":"2022-08-24","cited_by_count":40,"area":null},{"id":"2212.10785","title":"SERENGETI: Massively Multilingual Language Models for Africa","created":"2022-12-21","cited_by_count":40,"area":null},{"id":"2403.10691","title":"MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling","created":"2024-03-15","cited_by_count":40,"area":null},{"id":"2112.08804","title":"CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs","created":"2021-12-16","cited_by_count":39,"area":null},{"id":"2410.12705","title":"WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines","created":"2024-10-16","cited_by_count":39,"area":"mllm"},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2502.02481","title":"Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study","created":"2025-02-04","cited_by_count":38,"area":null},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2212.09660","title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2306.07377","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","created":"2023-06-12","cited_by_count":35,"area":null},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2310.15135","title":"Quantifying the Dialect Gap and its Correlates Across Languages","created":"2023-10-23","cited_by_count":33,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2309.08591","title":"Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings","created":"2023-09-15","cited_by_count":32,"area":"lr"},{"id":"2311.09205","title":"When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource Languages","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2410.15037","title":"mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation","created":"2024-10-19","cited_by_count":32,"area":null},{"id":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","cited_by_count":31,"area":null},{"id":"2205.04182","title":"Enhancing Cross-lingual Transfer by Manifold Mixup","created":"2022-05-09","cited_by_count":30,"area":null},{"id":"2205.12247","title":"GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models","created":"2022-05-24","cited_by_count":30,"area":null},{"id":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30,"area":null},{"id":"2305.09800","title":"Mirages: On Anthropomorphism in Dialogue Systems","created":"2023-05-16","cited_by_count":30,"area":null},{"id":"2402.19167","title":"Teaching Large Language Models an Unseen Language on the Fly","created":"2024-02-29","cited_by_count":30,"area":null},{"id":"2205.04086","title":"A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bank","created":"2022-05-09","cited_by_count":29,"area":null},{"id":"2206.09755","title":"Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold","created":"2022-06-20","cited_by_count":29,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2109.06050","title":"Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training","created":"2021-09-13","cited_by_count":28,"area":null}],"next_cursor":"100"}